ray0rf1re commited on
Commit
d55e015
·
verified ·
1 Parent(s): 5c04b05

Upload Qwen3ForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. config.json +71 -0
  3. generation_config.json +9 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,6 @@
1
  ---
2
  license: mit
 
 
 
3
  ---
 
1
  ---
2
  license: mit
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "neutral",
15
+ "2": "positive"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6144,
19
+ "label2id": {
20
+ "negative": 0,
21
+ "neutral": 1,
22
+ "positive": 2
23
+ },
24
+ "layer_types": [
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 40960,
55
+ "max_window_layers": 28,
56
+ "model_type": "qwen3",
57
+ "num_attention_heads": 16,
58
+ "num_hidden_layers": 28,
59
+ "num_key_value_heads": 8,
60
+ "pad_token_id": 151643,
61
+ "problem_type": "single_label_classification",
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000,
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": true,
67
+ "transformers_version": "4.57.6",
68
+ "use_cache": false,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645
5
+ ],
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.6",
8
+ "use_cache": false
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ab60cdf99d4ede770cede26e05241e5beaa9c90a6f1fa0ca6e1390008152f2
3
+ size 3441185296